AlignmentResearch/PineappleRLHF
Viewer
•
Updated
•
5.53k
•
225
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
AlignmentResearch/AdvBench
Viewer
•
Updated
•
1.04k
•
171
AlignmentResearch/ClearHarm
Viewer
•
Updated
•
7.52k
•
143
AlignmentResearch/PAPStrongREJECT
Viewer
•
Updated
•
10.9k
•
52
AlignmentResearch/DolusChat
Viewer
•
Updated
•
64.9k
•
110
AlignmentResearch/BoNClearHarm
Viewer
•
Updated
•
120k
•
33
AlignmentResearch/ReNeLLMClearHarm
Viewer
•
Updated
•
40k
•
34
AlignmentResearch/ReNeLLMStrongREJECT
Viewer
•
Updated
•
80k
•
132
AlignmentResearch/WildGuardTest
Viewer
•
Updated
•
6.27k
•
105
AlignmentResearch/PAPClearHarm
Viewer
•
Updated
•
4k
•
93
AlignmentResearch/SorryBenchFiltering
Viewer
•
Updated
•
2.86k
•
95
AlignmentResearch/DoNotAnswer
Viewer
•
Updated
•
264
•
76
AlignmentResearch/SorryBench
Viewer
•
Updated
•
240
•
37
AlignmentResearch/StrongREJECT
Viewer
•
Updated
•
387
•
165
AlignmentResearch/WildChat
Viewer
•
Updated
•
45.6k
•
20
AlignmentResearch/HarmBench
Viewer
•
Updated
•
400
•
32
AlignmentResearch/WildChatCurriculum
Viewer
•
Updated
•
13.2k
•
98
AlignmentResearch/JailbreakCompletionsCurriculum
Viewer
•
Updated
•
9.39k
•
27
AlignmentResearch/WildChatScored
Viewer
•
Updated
•
13k
•
10
AlignmentResearch/BoNStrongREJECT
Viewer
•
Updated
•
100k
•
32
AlignmentResearch/NestedCiphers
Viewer
•
Updated
•
806k
•
14
AlignmentResearch/AugmentedJailbreaks
Viewer
•
Updated
•
20.8k
•
5
AlignmentResearch/JailbreakCompletions
Viewer
•
Updated
•
46.3k
•
16
AlignmentResearch/WildChatFiltered
Viewer
•
Updated
•
24k
•
27
AlignmentResearch/JailbreakInputs
Viewer
•
Updated
•
102k
•
26
•
1
AlignmentResearch/Llama3Jailbreaks
Viewer
•
Updated
•
78.5k
•
309
AlignmentResearch/XSTest
Viewer
•
Updated
•
900
•
29
AlignmentResearch/WordLength
Viewer
•
Updated
•
100k
•
55
AlignmentResearch/Harmless
Viewer
•
Updated
•
86.6k
•
46
AlignmentResearch/Helpful
Viewer
•
Updated
•
88.1k
•
47